Neural Network Models for Empirical Finance
Open Access
- 30 October 2020
- journal article
- review article
- Published by MDPI AG in Journal of Risk and Financial Management
- Vol. 13 (11), 265
- https://doi.org/10.3390/jrfm13110265
Abstract
This paper presents an overview of the procedures that are involved in prediction with machine learning models with special emphasis on deep learning. We study suitable objective functions for prediction in high-dimensional settings and discuss the role of regularization methods in order to alleviate the problem of overfitting. We also review other features of machine learning methods, such as the selection of hyperparameters, the role of the architecture of a deep neural network for model prediction, or the importance of using different optimization routines for model selection. The review also considers the issue of model uncertainty and presents state-of-the-art methods for constructing prediction intervals using ensemble methods, such as bootstrap and Monte Carlo dropout. These methods are illustrated in an out-of-sample empirical forecasting exercise that compares the performance of machine learning methods against conventional time series models for different financial indices. These results are confirmed in an asset allocation context.Keywords
This publication has 19 references indexed in Scilit:
- Sparse Signals in the Cross‐Section of ReturnsThe Journal of Finance, 2018
- Robust inference on average treatment effects with possibly more covariates than observationsJournal of Econometrics, 2015
- Deep learningNature, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- High-Dimensional Methods and Inference on Structural and Treatment EffectsJournal of Economic Perspectives, 2014
- Forecasting and recombining time-series components by using neural networksJournal of the Operational Research Society, 2003
- A Comparison of Some Error Estimates for Neural Network ModelsNeural Computation, 1996
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Bootstrap Methods: Another Look at the JackknifeThe Annals of Statistics, 1979